Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that express interpersonal connections and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ety
    -0.19
    .cg
    -0.16
    rey
    -0.15
    ób
    -0.15
    zh
    -0.15
    mani
    -0.14
    ythe
    -0.14
    gren
    -0.14
    æ¤
    -0.14
    enor
    -0.14
    POSITIVE LOGITS
    found
    0.23
     find
    0.22
     found
    0.22
     finds
    0.22
    (find
    0.21
     Find
    0.21
    æī¾åĪ°
    0.20
    find
    0.19
    Find
    0.18
    -find
    0.18
    Act Density 0.049%

    No Known Activations